Skip to content

Revisit Agent Prompts #69

@neuromechanist

Description

@neuromechanist

Further testing of the agents show that the evaluation, faithfulness and conflict agents commonly lack catching semantic, meaning like grouping in parentheses. We should revisit the prompts to ensure that the additions in the annotation agent is properly tested and evaluated in other agents.

Metadata

Metadata

Labels

component: agentsRelated to LangGraph agentspriority: highHigh priority - important for upcoming releasetype: bugSomething isn't working correctly

Type

Projects

No projects

Relationships

None yet

Development

No branches or pull requests

Issue actions